Search Results for author:
Found 15 papers, 4 papers with code
Contrastive Loss is All You Need to Recover Analogies as Parallel Lines
While static word embedding models are known to represent linguistic analogies as parallel lines in high-dimensional space, the underlying mechanism as to why they result in such geometric structures remains obscure.
Improving Model Training via Self-learned Label Representations
In this work, we demonstrate that more sophisticated label representations are better for classification than the usual one-hot encoding.
A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level
We automatically synthesize programs using few-shot learning and OpenAI's Codex transformer and execute them to solve course problems at 81% automatic accuracy.
An analysis of document graph construction methods for AMR summarization
Prior work in AMR-based summarization has automatically merged the individual sentence graphs into a document graph, but the method of merging and its effects on summary content selection have not been independently evaluated.
Solving Probability and Statistics Problems by Program Synthesis
Our work is the first to introduce a new dataset of university-level probability and statistics problems and solve these problems in a scalable fashion using the program synthesis capabilities of large language models.
Solving Linear Algebra by Program Synthesis
We solve MIT's Linear Algebra 18. 06 course and Columbia University's Computational Linear Algebra COMS3251 courses with perfect accuracy by interactive program synthesis.
Automated Symbolic Law Discovery: A Computer Vision Approach
This is not a trivial problem as it involves searching for a complex mathematical relationship over a large set of explanatory variables and operators that can be combined in an infinite number of ways.
Biased Programmers? Or Biased Data? A Field Experiment in Operationalizing AI Ethics
We find that biased predictions are mostly caused by biased training data.
Meta-Learning to Cluster
By providing multiple types of training datasets as inputs, our model has the ability to generalize well on unseen datasets (new clustering tasks).
Model-Agnostic Meta-Learning using Runge-Kutta Methods
By leveraging this refined control, we demonstrate that there are multiple principled ways to update MAML and show that the classic MAML optimization is simply a special case of second-order Runge-Kutta method that mainly focuses on fast-adaptation.
Metric Learning on Manifolds
Recent literature has shown that symbolic data, such as text and graphs, is often better represented by points on a curved manifold, rather than in Euclidean space.
Noise-tolerant fair classification
We finally show that our procedure is empirically effective on two case-studies involving sensitive feature censoring.
Stochastic Neighbor Embedding under f-divergences
A common concern with $t$-SNE criterion is that it is optimized using gradient descent, and can become stuck in poor local minima.
Sample complexity of learning Mahalanobis distance metrics
Metric learning seeks a transformation of the feature space that enhances prediction quality for the given task at hand.
Learning the structure of manifolds using random projections
We present a simple variant of the k-d tree which automatically adapts to intrinsic low dimensional structure in data.
